# SAMPLE NAME
## specify sample name
sample.name <- c("beau", "ophio_cflo", "ophio_kim")
## color scheme for the samples
col.scheme <- c("#5A829F", "#AD212F", "black")

# SCRIPT NAME
## specify the name of the script (folder) where figures will be saved
script.name <- "01_comparing_gene_exp_ophio_beau"

# eJTK OUTPUT
## Set GammaP threshold below which genes are classified as rhythmic
gamma.pval = 0.05
## Set false discovery rate for functional enrichment analyses
FDR = 5
# LOAD DATABASES (TC7)
# 1. TC6_ejtk.db
# Desc: This database contains all ejtk-output for TC6
ejtk.db <- dbConnect(RSQLite::SQLite(), paste0(path_to_repo,"/data/databases/TC6_fungal_ejtk.db"))
# which tables are in the database
src_dbi(ejtk.db)
## src:  sqlite 3.29.0 [/Users/biplabendudas/Documents/GitHub/Das_et_al_2022a/data/databases/TC6_fungal_ejtk.db]
## tbls: beau_rhythmic_genes_12h, beau_rhythmic_genes_24h, beau_zscores_08h,
##   beau_zscores_12h, beau_zscores_24h, ophio_cflo_rhythmic_genes_12h,
##   ophio_cflo_rhythmic_genes_24h, ophio_cflo_zscores_08h,
##   ophio_cflo_zscores_12h, ophio_cflo_zscores_24h, ophio_kim_DD_zscores_24h,
##   ophio_kim_LD_rhythmic_genes_24h, ophio_kim_LD_zscores_24h
#
# 2. TC6_data.db
data.db <- dbConnect(RSQLite::SQLite(), paste0(path_to_repo,"/data/databases/TC6_fungal_data.db"))
src_dbi(data.db)
## src:  sqlite 3.29.0 [/Users/biplabendudas/Documents/GitHub/Das_et_al_2022a/data/databases/TC6_fungal_data.db]
## tbls: beau_expressed_genes, beau_fpkm, beau_log2fpkm, beau_zscores,
##   ophio_cflo_expressed_genes, ophio_cflo_fpkm, ophio_cflo_log2fpkm,
##   ophio_cflo_zscores, ophio_kim_DD_expressed_genes, ophio_kim_DD_fpkm,
##   ophio_kim_DD_log2fpkm, ophio_kim_DD_zscores, ophio_kim_expressed_genes,
##   ophio_kim_fpkm, ophio_kim_log2fpkm, ophio_kim_zscores
#

Overview/Goals

1. General patterns of gene expression

# number of all genes
all.genes <- list()
for (i in 1:length(sample.name)) {
  all.genes[[i]] <- tbl(data.db, paste0(sample.name[[i]] ,"_fpkm")) %>%  
    collect()
  
  writeLines(paste("Number of genes in", sample.name[[i]], ":", nrow(all.genes[[i]])))
}
## Number of genes in beau : 10364
## Number of genes in ophio_cflo : 7455
## Number of genes in ophio_kim : 8577
# A1: genes that have NO expression (FPKM == 0 at all time points)
not.expressed <- list()
for (i in 1:length(sample.name)) {
  not.expressed[[i]] <-
    tbl(data.db, paste0(sample.name[[i]] ,"_fpkm")) %>% 
    collect() %>% 
    filter_at(vars(starts_with("Z")), all_vars(. == 0)) %>%
    pull(gene_name)
  
  # How many genes are not expressed?
  writeLines(paste("n(genes-NOT-EXPRESSED) in", sample.name[[i]], ":", length(not.expressed[[i]])))
  
}
## n(genes-NOT-EXPRESSED) in beau : 759
## n(genes-NOT-EXPRESSED) in ophio_cflo : 190
## n(genes-NOT-EXPRESSED) in ophio_kim : 111
# A2: run enrichment (make plot of enrichment found of non-expressed genes)
for (i in 1:length(sample.name)) {
  writeLines(paste("running GO enrichment for NOT-EXPRESSED genes in", sample.name[[i]]))
  # run enrichment
  not.expressed[[i]] %>% 
    go_enrichment(., 
                  org = sample.name[[i]], 
                  function.dir = path_to_repo,
                  bg = 'all') %>% # enrichment against all ophio_cflo genes in the genome
    
    # # pull gene names for a given GO term
    # separate_rows(., gene_name, sep = ", ") %>%
    # filter(GO == "GO:0009405") %>% # pathogenesis
    # # filter(GO == "GO:0090729") %>% # toxin activity
    # # filter(GO == "GO:0044419") %>% # interspecies interaction between organisms
    # # filter(GO == "GO:0020037") %>% # heme binding
    # pull()
    
    go_enrichment_plot(clean = "no",
                       function.dir = path_to_repo) %>% 
    print()
  
}
## running GO enrichment for NOT-EXPRESSED genes in beau
## [1] "Loading annotation file for Beauveria bassiana"
## [1] "Done."
## [1] "Number of genes in background geneset: 10364"
## [1] "Number of genes in the test set: 759"
## [1] "--------------------------------"
## [1] "Number of GO terms in background geneset: 2456"
## [1] "Number of GO terms (at least 5genes) in background geneset: 925"
## [1] "Number of GO terms (at least 5genes) in test set: 140"
## [1] "Testing for enrichment..."

## running GO enrichment for NOT-EXPRESSED genes in ophio_cflo
## [1] "Loading annotation file for Ophiocordyceps camponoti-floridani"
## [1] "Done."
## [1] "Number of genes in background geneset: 7455"
## [1] "Number of genes in the test set: 190"
## [1] "--------------------------------"
## [1] "Number of GO terms in background geneset: 2400"
## [1] "Number of GO terms (at least 5genes) in background geneset: 844"
## [1] "Number of GO terms (at least 5genes) in test set: 50"
## [1] "Testing for enrichment..."

## running GO enrichment for NOT-EXPRESSED genes in ophio_kim
## [1] "Loading annotation file for Ophiocordyceps kimflemingae"
## [1] "Done."
## [1] "Number of genes in background geneset: 8441"
## [1] "Number of genes in the test set: 111"
## [1] "--------------------------------"
## [1] "Number of GO terms in background geneset: 1099"
## [1] "Number of GO terms (at least 5genes) in background geneset: 279"
## [1] "Number of GO terms (at least 5genes) in test set: 4"
## [1] "Testing for enrichment..."

# B: genes that are expressed (FPKM > 1 for at least one time point)
expressed <- list()
for (i in 1:length(sample.name)) {
  expressed[[i]] <- 
    tbl(data.db, paste0(sample.name[[i]],"_expressed_genes")) %>% 
    filter(expressed=="yes") %>% 
    collect() %>% 
    pull(gene_name) 
  
  # How many genes are expressed?
  writeLines(paste("n(EXPRESSED) in", sample.name[[i]], ":", length(expressed[[i]])))
}
## n(EXPRESSED) in beau : 9006
## n(EXPRESSED) in ophio_cflo : 6998
## n(EXPRESSED) in ophio_kim : 8150

2. Daily rhythms in gene expression

## Load all the rhythmic genesets 
## Note, ordered according to their p-value; highly rhythmic at the top.
#
# Choose period
period = '24'

## 
rhy <- list()
for (i in 1:2) {
  rhy[[i]] <-
    tbl(ejtk.db, paste0(sample.name[[i]],"_zscores_",period,'h')) %>%
    filter(GammaP < gamma.pval) %>%
    select(ID, GammaP) %>% collect() %>% arrange(GammaP) %>%
    select(ID) %>% pull()
  
  # How many genes are rythmic?
  writeLines(paste0("n(rhythmic-",period, "h) in ", sample.name[[i]], " : ", length(rhy[[i]])))
}
## n(rhythmic-24h) in beau : 1872
## n(rhythmic-24h) in ophio_cflo : 2285

Hierarchical clustering of rhy24

  • perform hierarchical clustering of 24h-rhythmic genes into four clusters;
  • plot time-course heatmaps for the clustered 24h-rhythmic geneset
  • Identify the day-peaking and night-peaking clusters visually.
# Choose period
period = '24'

## 
rhy <- list()
for (i in 1:2) {
  rhy[[i]] <-
    tbl(ejtk.db, paste0(sample.name[[i]],"_zscores_",period,'h')) %>%
    filter(GammaP < gamma.pval) %>%
    select(ID, GammaP) %>% collect() %>% arrange(GammaP) %>%
    select(ID) %>% pull()
  
  # How many genes are rythmic?
  writeLines(paste0("n(rhythmic-",period, "h) in ", sample.name[[i]], " : ", length(rhy[[i]])))
}
## n(rhythmic-24h) in beau : 1872
## n(rhythmic-24h) in ophio_cflo : 2285
## initialise lists to hold input and output of the hierarchical clustering
zscore.dat <- list() # zscore data (input)
my_gene_col <- list() # cluster identity for each rhythmic gene (output)
rhy.heat <- list() # pheatmap that can be saved/plotted (output)

# specify number of clusters
n_clusters <- 4

## run clustering and plot
for (i in 1:2) {
  ## load zscore dataset
  zscore.dat[[i]] <- data.db %>% tbl(., paste0(sample.name[[i]],"_zscores")) %>% collect()
  
  # Filter the zscores to keep only rhythmic genes
  zscore.rhy <-
    zscore.dat[[i]] %>% 
    filter(gene_name %in% rhy[[i]]) %>% 
    as.data.frame()
  
  # Set genes as rownames and convert it into a matrix
  rownames(zscore.rhy) = zscore.rhy$gene_name
  zscore.rhy <- as.matrix(zscore.rhy[-1])
  
  
  # Hierarchical clustering of the genesets
  my_hclust_gene <- hclust(dist(zscore.rhy), method = "complete")
  
  
  # Make annotations for the heatmaps
  my_clusters <- cutree(tree = as.dendrogram(my_hclust_gene), k = n_clusters) # k=  clusters
  my_gene_col[[i]] <- data.frame(cluster = my_clusters)
  
  
  # I’ll add some column annotations and create the heatmap.
  # Annotations for:
  # 1. Is the sample collected during the light or dark phase? 
  my_sample_col <- data.frame(phase = rep(c("light", "dark", "light"), c(5,6,1)))
  row.names(my_sample_col) <- colnames(zscore.rhy)
  
  # Manual color palette
  my_colour = list(
    phase = c(light = "#F2E205", dark = "#010440"),
    cluster = viridis::cividis(100)[c(10,90,60,30)]) #### NEED TO CHANGE #### account for n_clusters
  
  # Color scale
  my.breaks = seq(min(zscore.rhy), max(zscore.rhy), by=0.1)
  # my.breaks = seq(min(zscore.rhy), max(zscore.rhy), by=0.06)
  
  # Let's plot!
  rhy.heat[[i]] <-
    pheatmap(zscore.rhy, show_rownames = F, show_colnames = F,
             annotation_row = my_gene_col[[i]], 
             annotation_col = my_sample_col,
             cutree_rows = n_clusters, # OG was 4
             cutree_cols = 2,
             annotation_colors = my_colour,
             border_color=FALSE,
             cluster_cols = F,
             breaks = my.breaks,
             ## color scheme borrowed from: 
             color = inferno(length(my.breaks) - 1),
             # treeheight_row = 0, 
             # treeheight_col = 0,
             # remove the color scale or not
             main = paste0(sample.name[[i]], " 24h-rhythmic \n (n=", nrow(zscore.rhy), " genes)"),
             ## annotation legend
             annotation_legend = T,
             ## Color scale
             legend = T)
  
}

Phase plots

rhy.24.sig <- list()
phase.ejtk <- list()

# Obtain the phases of 24h-rhythmic genes beau v. ophio_cflo
for (i in 1:2) {

rhy.24.sig[[i]] <- 
  tbl(ejtk.db, paste0(sample.name[i],"_zscores_24h")) %>% 
  filter(GammaP < gamma.pval) %>% 
  collect()

# Get the phases of the best matched waveforms
phase.ejtk[[i]] <- circular::circular(rhy.24.sig[[i]]$Phase, units="hours", template="clock24")
# # Get the time-of-day of expression peak
# phase.ejtk[[i]] <- circular::circular(rhy.24.sig[[i]]$MaxLoc, units="hours", template="clock24")
# # Get the time-of-day of expression trough
# phase.ejtk[[i]] <- circular::circular(rhy.24.sig[[i]]$MinLoc, units="hours", template="clock24")

}

# save all the circular phases in a list
l.phases <- phase.ejtk
# let's name the list elements for later use and reference
names(l.phases) <- sample.name[1:2]

writeLines("Performing Watson test to check if the average peak of 24h-rhythms in Beau and Ophio-cflo differs significantly")
## Performing Watson test to check if the average peak of 24h-rhythms in Beau and Ophio-cflo differs significantly
# For all rhy genes
beau.ophio <- watson.two.test(l.phases[[1]],l.phases[[2]], alpha = FDR/100)
writeLines("Beau v. Ophio-cflo")
## Beau v. Ophio-cflo
beau.ophio %>% print()
## 
##       Watson's Two-Sample Test of Homogeneity 
## 
## Test Statistic: 5.9634 
## Level 0.05 Critical Value: 0.187 
## Reject Null Hypothesis
## Plot the phase distributions

# Initialize a list for saving the ggplots
g <- list()

means <- as.numeric(lapply(phase.ejtk, mean))
means <- circular(means, units="hours", template="clock24")


for(i in 1:length(l.phases)) {
  
  # define phase levels
  ordered_phases <- c("2","4","6","8","10","12",
                      "14","16","18","20","22","24")
    
  df.test <- l.phases[[i]] %>%
    as.data.frame() %>% 
    mutate(phase = x) %>%
    mutate(phase = replace(phase, x=="0", "24")) %>% 
    select(-x) %>% 
    group_by(phase = factor(phase, levels = ordered_phases)) %>%
    summarise(n_genes = n())

  m <- as.numeric(means[i])
    
  g[[i]] <-
    ggplot(df.test, aes(x=factor(phase), y=n_genes)) + 
    geom_bar(stat='identity', fill=col.scheme[[i]]) +
    
    xlab(c(names(l.phases)[i])) +
    
    scale_y_continuous(breaks = c(0,200,400,600)) +
    
    coord_polar() +
    theme_Publication() +
    theme(text = element_text(size = 15, colour = 'black'),
              # axis.title.x=element_blank(),
              # axis.text.x=element_blank(),
              legend.position = "none")
    #ggtitle(paste0("Dataset: ", names(l.phases)[i])) 
  
}

ggpubr::ggarrange(plotlist=g,
                  nrow = 2, ncol = 1,
                  widths = c(1,2), labels = NA)

Clusters of rhythmic genes

  • Which processes are identified clusters of rhythmic genes involved in?
  • How do they fluctuate throughout the day?

Beau - 24h

for (i in 1:n_clusters){
  
  writeLines(paste0("Species: ", sample.name[[1]], "\n", "24h-rhythmic genes, Cluster: ", i))
  
  # Summary
  genes <- my_gene_col[[1]] %>% rownames_to_column("g") %>% filter(cluster==as.character(i)) %>% pull(g)
  writeLines(paste0("n(genes) = ", length(genes),"\n"))
  
  # Enrichment
  overrepresented.terms <-
    genes %>% 
      go_enrichment(.,
                    function.dir = path_to_repo,
                    org = sample.name[[1]],
                    bg = expressed[[1]]) %>% 
      filter(adj_pVal < FDR/100) %>% 
      filter(over_under == "over")
  writeLines(paste0("\n", "n(overrepresented terms) = ", nrow(overrepresented.terms), "\n"))
  
  # Enriched terms word-cloud (borrowed from: https://towardsdatascience.com/create-a-word-cloud-with-r-bde3e7422e8a)
  if (nrow(overrepresented.terms)>0){
    # load libraries
    pacman::p_load(tm, wordcloud, RColorBrewer, wordcloud2)
    # get text as a character vector
    text <- overrepresented.terms %>% pull(GO_desc)
    # load your text data as a corpus
    docs <- Corpus(VectorSource(text)) # requires library "tm"
    # clean text (necessary?)
    docs <- docs %>%
              tm_map(removeNumbers) %>%
              tm_map(removePunctuation) %>%
              tm_map(stripWhitespace)
    docs <- tm_map(docs, content_transformer(tolower))
    docs <- tm_map(docs, removeWords, c("process", "molecular","cellular",
                                        "component", "compound", "part",
                                        "activity", "acid"
                                        ))
    # create document-term-matrix
    dtm <- TermDocumentMatrix(docs) 
    matrix <- as.matrix(dtm) 
    words <- sort(rowSums(matrix),decreasing=TRUE) 
    df <- data.frame(word = names(words),freq=words)
    # generate word-cloud
    wordcloud::wordcloud(words = df$word, freq = df$freq, min.freq = 2,
              max.words=200, random.order=FALSE, rot.per=0.35,
              scale=c(5,0.15),
              # colors=brewer.pal(8, "Dark2")
              colors=col.scheme[[1]]
              )
    
    ## save overrepresented GO terms for REVIGO analyses
      overrepresented.terms %>% select(GO, adj_pVal) %>% 
        readr::write_tsv(., paste0(path_to_repo,"/results/go_temp_files/",sample.name[[1]],"_Cluster_",i,".txt"))
      
  }
  # Stacked zplot
  genes %>% 
  stacked.zplot_tc6(cond = "beau") %>% 
    multi.plot(rows = 1, cols = 1)
  
}
## Species: beau
## 24h-rhythmic genes, Cluster: 1
## n(genes) = 767
## 
## [1] "Loading annotation file for Beauveria bassiana"
## [1] "Done."
## [1] "Number of genes in background geneset: 9006"
## [1] "Number of genes in the test set: 767"
## [1] "--------------------------------"
## [1] "Number of GO terms in background geneset: 2453"
## [1] "Number of GO terms (at least 5genes) in background geneset: 898"
## [1] "Number of GO terms (at least 5genes) in test set: 235"
## [1] "Testing for enrichment..."
## 
## n(overrepresented terms) = 143

## Species: beau
## 24h-rhythmic genes, Cluster: 2
## n(genes) = 550
## 
## [1] "Loading annotation file for Beauveria bassiana"
## [1] "Done."
## [1] "Number of genes in background geneset: 9006"
## [1] "Number of genes in the test set: 550"
## [1] "--------------------------------"
## [1] "Number of GO terms in background geneset: 2453"
## [1] "Number of GO terms (at least 5genes) in background geneset: 898"
## [1] "Number of GO terms (at least 5genes) in test set: 179"
## [1] "Testing for enrichment..."
## 
## n(overrepresented terms) = 2

## Species: beau
## 24h-rhythmic genes, Cluster: 3
## n(genes) = 337
## 
## [1] "Loading annotation file for Beauveria bassiana"
## [1] "Done."
## [1] "Number of genes in background geneset: 9006"
## [1] "Number of genes in the test set: 337"
## [1] "--------------------------------"
## [1] "Number of GO terms in background geneset: 2453"
## [1] "Number of GO terms (at least 5genes) in background geneset: 898"
## [1] "Number of GO terms (at least 5genes) in test set: 144"
## [1] "Testing for enrichment..."
## 
## n(overrepresented terms) = 0

## Species: beau
## 24h-rhythmic genes, Cluster: 4
## n(genes) = 218
## 
## [1] "Loading annotation file for Beauveria bassiana"
## [1] "Done."
## [1] "Number of genes in background geneset: 9006"
## [1] "Number of genes in the test set: 218"
## [1] "--------------------------------"
## [1] "Number of GO terms in background geneset: 2453"
## [1] "Number of GO terms (at least 5genes) in background geneset: 898"
## [1] "Number of GO terms (at least 5genes) in test set: 122"
## [1] "Testing for enrichment..."
## 
## n(overrepresented terms) = 36

Ophio-cflo - 24h

for (i in 1:n_clusters){
  
  writeLines(paste0("Species: ", sample.name[[2]], "\n", "24h-rhythmic genes, Cluster: ", i))
  
  # Summary
  genes <- my_gene_col[[2]] %>% rownames_to_column("g") %>% filter(cluster==as.character(i)) %>% pull(g)
  writeLines(paste0("n(genes) = ", length(genes),"\n"))
  
  # Enrichment
  overrepresented.terms <-
    genes %>% 
      go_enrichment(.,
                    function.dir = path_to_repo,
                    org = sample.name[[2]],
                    bg = expressed[[2]]) %>% 
      filter(adj_pVal < FDR/100) %>% 
      filter(over_under == "over")
  writeLines(paste0("\n", "n(overrepresented terms) = ", nrow(overrepresented.terms), "\n"))
  
  # Enriched terms word-cloud (borrowed from: https://towardsdatascience.com/create-a-word-cloud-with-r-bde3e7422e8a)
    if (nrow(overrepresented.terms) > 0) {
      # load libraries
      pacman::p_load(tm, wordcloud, RColorBrewer, wordcloud2)
      # get text as a character vector
      text <- overrepresented.terms %>% pull(GO_desc)
      # load your text data as a corpus
      docs <- Corpus(VectorSource(text)) # requires library "tm"
      # clean text (necessary?)
      docs <- docs %>%
                tm_map(removeNumbers) %>%
                tm_map(removePunctuation) %>%
                tm_map(stripWhitespace)
      docs <- tm_map(docs, content_transformer(tolower))
      docs <- tm_map(docs, removeWords, c("process", "molecular","cellular",
                                          "component", "compound", "part",
                                          "activity", "acid"
                                          ))
      # create document-term-matrix
      dtm <- TermDocumentMatrix(docs) 
      matrix <- as.matrix(dtm) 
      words <- sort(rowSums(matrix),decreasing=TRUE) 
      df <- data.frame(word = names(words),freq=words)
      # generate word-cloud
      wordcloud::wordcloud(words = df$word, freq = df$freq, min.freq = 2,
                max.words=200, random.order=FALSE, rot.per=0.35,
                scale=c(4,0.15),
                # colors=brewer.pal(8, "Dark2")
                colors=col.scheme[[2]]
                )
      
      ## save overrepresented GO terms for REVIGO analyses
      overrepresented.terms %>% select(GO, adj_pVal) %>% 
        # readr::write_tsv(., paste0("./results/go_temp_files/",sample.name[[2]],"_Cluster_",i,".txt"))
        write.table(., paste0(path_to_repo,"/results/go_temp_files/",sample.name[[2]],"_Cluster_",i,".csv"),
                    sep = ",",
                    row.names = F, col.names = F)
      
    }
  
  
  # Stacked zplot
  genes %>% 
  stacked.zplot_tc6(cond = "ophio_cflo") %>% 
    multi.plot(rows = 1, cols = 1)
  
}
## Species: ophio_cflo
## 24h-rhythmic genes, Cluster: 1
## n(genes) = 833
## 
## [1] "Loading annotation file for Ophiocordyceps camponoti-floridani"
## [1] "Done."
## [1] "Number of genes in background geneset: 6998"
## [1] "Number of genes in the test set: 833"
## [1] "--------------------------------"
## [1] "Number of GO terms in background geneset: 2359"
## [1] "Number of GO terms (at least 5genes) in background geneset: 831"
## [1] "Number of GO terms (at least 5genes) in test set: 221"
## [1] "Testing for enrichment..."
## 
## n(overrepresented terms) = 83

## Species: ophio_cflo
## 24h-rhythmic genes, Cluster: 2
## n(genes) = 465
## 
## [1] "Loading annotation file for Ophiocordyceps camponoti-floridani"
## [1] "Done."
## [1] "Number of genes in background geneset: 6998"
## [1] "Number of genes in the test set: 465"
## [1] "--------------------------------"
## [1] "Number of GO terms in background geneset: 2359"
## [1] "Number of GO terms (at least 5genes) in background geneset: 831"
## [1] "Number of GO terms (at least 5genes) in test set: 158"
## [1] "Testing for enrichment..."
## 
## n(overrepresented terms) = 31

## Species: ophio_cflo
## 24h-rhythmic genes, Cluster: 3
## n(genes) = 354
## 
## [1] "Loading annotation file for Ophiocordyceps camponoti-floridani"
## [1] "Done."
## [1] "Number of genes in background geneset: 6998"
## [1] "Number of genes in the test set: 354"
## [1] "--------------------------------"
## [1] "Number of GO terms in background geneset: 2359"
## [1] "Number of GO terms (at least 5genes) in background geneset: 831"
## [1] "Number of GO terms (at least 5genes) in test set: 158"
## [1] "Testing for enrichment..."
## 
## n(overrepresented terms) = 30

## Species: ophio_cflo
## 24h-rhythmic genes, Cluster: 4
## n(genes) = 633
## 
## [1] "Loading annotation file for Ophiocordyceps camponoti-floridani"
## [1] "Done."
## [1] "Number of genes in background geneset: 6998"
## [1] "Number of genes in the test set: 633"
## [1] "--------------------------------"
## [1] "Number of GO terms in background geneset: 2359"
## [1] "Number of GO terms (at least 5genes) in background geneset: 831"
## [1] "Number of GO terms (at least 5genes) in test set: 242"
## [1] "Testing for enrichment..."
## 
## n(overrepresented terms) = 123

Reduce redundant GO terms

Two options to do this:

Option #1: Get the list of overrepresented GO terms and their associated p-values and use REVIGO portal online to reduce the redundant terms

Option #2: Use the scripts provided by REVIGO to programmatically run REVIGO using bash/R. For more information see (here)[http://revigo.irb.hr/FAQ.aspx#q07] Status: tried running it via bash, and it didn’t work; NEED TO FIGURE IT OUT.

3. Beau v. Ophio - 24h-rhy

Next, we compare the homologous genes in both the fungi to understand if the rhythmic genes (and processes) in the two fungi are similar or not; also, is there any differences in the daily expression of these genes between the two fungal parasites?

Obtain homology data

# Read the source file
homology.file <- "ophio_beau_homology.csv"
homology.file <- 
  paste0(path_to_repo, "/results/proteinortho/", homology.file) %>% 
  read.csv(., stringsAsFactors = F, na.strings = c(" ","","NA"))

# Clean the source file to keep distinct gene-gene homologs
homology.dat <-
  homology.file %>% 
  # names() %>% 
  select(ophio_gene, beau_gene) %>% 
  na.omit() %>% 
  distinct() %>% 
  group_by(beau_gene) %>% 
  filter(n()==1) %>% 
  select(beau_gene, ophio_gene)

writeLines(paste("Of the", length(expressed[[2]]), "genes expressed in Ophio-cflo,",
                 "and", length(expressed[[1]]), "genes expressed in Beau",
                 nrow(homology.dat), "genes show one-to-one orthology"))
## Of the 6998 genes expressed in Ophio-cflo, and 9006 genes expressed in Beau 5274 genes show one-to-one orthology

Summarize the results

for (i in 1:2){
  
  # exp.dat <- expressed[[i]]
  rhy.dat <- rhy[[i]]
  ortho.dat <- homology.dat %>% pull(i) 

  listInput <- list(rhy.dat, ortho.dat)
  names(listInput) <- c(paste0(sample.name[[i]], c("_rhy24","_ortho")))
  
  library(UpSetR)
  library(viridis)
  # caste.col <- c("#F23030","#1A80D9")
  upset(fromList(listInput), 
        number.angles = 0, point.size = 3, line.size = 1.5, 
        mainbar.y.label = "Number of overlapping genes", 
        sets.x.label = "Sig. rhy genes", 
        text.scale = c(1.5, # y-axis label ("# overlapping genes")
                       2, # y-axis tick labels ("1000, 2000,..")
                       1.5, # label for histogram ("sig. rhy genes")
                       1, # tick labels for histogram
                       1.5, # set names ("Cflo-brain_08h,..") 
                       1.5),
        sets = names(listInput),
        nintersects = 15,
        keep.order = T,
        sets.bar.color = viridis(1),
        # adding queries
        query.legend = "bottom"
        ) %>% 
    print()
}

Rhy24 genes w/ orthologs

rhy.homology.dat <- 
  homology.dat %>% 
  filter(beau_gene %in% rhy[[1]] | ophio_gene %in% rhy[[2]])

Hierarchical clustering

### Make the dataframe for plotting
zscore.rhy.homology.dat <-
  zscore.dat[[1]] %>% 
  filter(gene_name %in% rhy.homology.dat[[1]]) %>% 
  rename_at(vars(starts_with("ZT")), ~ (gsub("A", "B", .x, fixed = TRUE))) %>% # fix colnames for beau
  # add ophio homologs for the beau genes
  left_join(rhy.homology.dat, by=c("gene_name" = "beau_gene")) %>%
  # remove the beau names and keep the ophio names only
  select(-1) %>% 
  select(gene_name = ophio_gene, everything()) %>% 
  # join ophio-cflo data
  left_join(zscore.dat[[2]], by="gene_name") %>%
  # drop any genes without expression values (NA)
  na.omit() %>% 
  as.data.frame() %>% 
  # set genes as rownames
  column_to_rownames("gene_name")

# Set genes as rownames and convert it into a matrix
# rownames(zscore.rhy.homology.dat) = zscore.rhy.homology.dat$gene_name
zscore.rhy.homology.dat <- as.matrix(zscore.rhy.homology.dat)


# Hierarchical clustering of the genesets
my_hclust_gene <- hclust(dist(zscore.rhy.homology.dat), method = "complete")


# Make annotations for the heatmaps
n_clusters <- 4
my_clusters <- cutree(tree = as.dendrogram(my_hclust_gene), k = n_clusters) # k=  clusters
my_gene_col <- data.frame(cluster = my_clusters)


# I’ll add some column annotations and create the heatmap.
# Annotations for:
# 1. Is the sample collected during the light or dark phase? 
my_sample_col <- data.frame(phase = rep(rep(c("light", "dark", "light"),c(5,6,1)),2),
                            conds = rep(c("beau", "ophio_cflo"), each=12))
row.names(my_sample_col) <- colnames(zscore.rhy.homology.dat)

# Manual color palette
my_colour = list(
  phase = c(light = "#F2E205", dark = "#010440"),
  conds = c(beau = "#5A829F", ophio_cflo = "#AD212F"),
  cluster = viridis::cividis(100)[c(10,90,60,30)]) #### NEED TO CHANGE #### account for n_clusters

# Color scale
my.breaks = seq(min(zscore.rhy.homology.dat), max(zscore.rhy.homology.dat), by=0.1)
# my.breaks = seq(min(zscore.rhy), max(zscore.rhy), by=0.06)

# Let's plot!
pheatmap(zscore.rhy.homology.dat, show_rownames = F, show_colnames = F,
           annotation_row = my_gene_col, 
           annotation_col = my_sample_col,
           cutree_rows = n_clusters, # OG was 4
           cutree_cols = 4,
           annotation_colors = my_colour,
           border_color=FALSE,
           cluster_cols = F,
           breaks = my.breaks,
           ## color scheme borrowed from: 
           color = inferno(length(my.breaks) - 1),
           # treeheight_row = 0, 
           # treeheight_col = 0,
           # remove the color scale or not
           main = paste0("24h-rhythmic \n (n=",
                         nrow(zscore.rhy.homology.dat), " orthologous genes)"),
           ## annotation legend
           annotation_legend = T,
           ## Color scale
           legend = T)

Individual clusters

for (j in 1:2) {
  
  for (i in 1:n_clusters){
    
    writeLines(paste0("Species: ", sample.name[[j]], "\n", "24h-rhythmic genes, Cluster: ", i))
    
    # Summary
    genes <- my_gene_col %>% rownames_to_column("g") %>% filter(cluster==as.character(i)) %>% pull(g)
    writeLines(paste0("n(genes) = ", length(genes),"\n"))
    
    # define the background geneset for enrichment analysis
    bg.genes <- homology.dat %>% pull(ophio_gene) %>% unique()
    
    ## Transform gene names (ophio -> beau) and refine background geneset
    if (j == 1) {
      genes <- 
        homology.dat %>% 
        filter(ophio_gene %in% genes) %>% 
        pull(beau_gene)
      bg.genes <- homology.dat %>% pull(beau_gene) %>% unique()
    }
    
    # Enrichment
    overrepresented.terms <-
      genes %>% 
        go_enrichment(.,
                      function.dir = path_to_repo,
                      org = sample.name[[j]],
                      bg = expressed[[j]]) %>% 
        filter(adj_pVal < FDR/100) %>% 
        filter(over_under == "over")
    writeLines(paste0("\n", "n(overrepresented terms) = ", nrow(overrepresented.terms), "\n"))
    
    # Enriched terms word-cloud (borrowed from: https://towardsdatascience.com/create-a-word-cloud-with-r-bde3e7422e8a)
    if (nrow(overrepresented.terms)>0){
      # load libraries
      pacman::p_load(tm, wordcloud, RColorBrewer, wordcloud2)
      # get text as a character vector
      text <- overrepresented.terms %>% pull(GO_desc)
      # load your text data as a corpus
      docs <- Corpus(VectorSource(text)) # requires library "tm"
      # clean text (necessary?)
      docs <- docs %>%
                tm_map(removeNumbers) %>%
                tm_map(removePunctuation) %>%
                tm_map(stripWhitespace)
      docs <- tm_map(docs, content_transformer(tolower))
      docs <- tm_map(docs, removeWords, c("process", "molecular","cellular",
                                          "component", "compound", "part",
                                          "activity", "acid"
                                          ))
      # create document-term-matrix
      dtm <- TermDocumentMatrix(docs) 
      matrix <- as.matrix(dtm) 
      words <- sort(rowSums(matrix),decreasing=TRUE) 
      df <- data.frame(word = names(words),freq=words)
      # generate word-cloud
      wordcloud::wordcloud(words = df$word, freq = df$freq, min.freq = 2,
                max.words=200, random.order=FALSE, rot.per=0,
                scale=c(4,0.15),
                # colors=brewer.pal(8, "Dark2")
                colors=col.scheme[[j]]
                )
      
      # ## save overrepresented GO terms for REVIGO analyses
      #   overrepresented.terms %>% select(GO, adj_pVal) %>% 
      #     readr::write_tsv(., paste0(path_to_repo,"/results/go_temp_files/",
      #                                sample.name[[1]],"_Cluster_",i,".txt"))
        
    }
    # Stacked zplot
    genes %>% 
    stacked.zplot_tc6(cond = sample.name[[j]]) %>% 
      multi.plot(rows = 1, cols = 1)
    
  }
}
## Species: beau
## 24h-rhythmic genes, Cluster: 1
## n(genes) = 718
## 
## [1] "Loading annotation file for Beauveria bassiana"
## [1] "Done."
## [1] "Number of genes in background geneset: 9006"
## [1] "Number of genes in the test set: 718"
## [1] "--------------------------------"
## [1] "Number of GO terms in background geneset: 2453"
## [1] "Number of GO terms (at least 5genes) in background geneset: 898"
## [1] "Number of GO terms (at least 5genes) in test set: 267"
## [1] "Testing for enrichment..."
## 
## n(overrepresented terms) = 154

## Species: beau
## 24h-rhythmic genes, Cluster: 2
## n(genes) = 1026
## 
## [1] "Loading annotation file for Beauveria bassiana"
## [1] "Done."
## [1] "Number of genes in background geneset: 9006"
## [1] "Number of genes in the test set: 1026"
## [1] "--------------------------------"
## [1] "Number of GO terms in background geneset: 2453"
## [1] "Number of GO terms (at least 5genes) in background geneset: 898"
## [1] "Number of GO terms (at least 5genes) in test set: 263"
## [1] "Testing for enrichment..."
## 
## n(overrepresented terms) = 134

## Species: beau
## 24h-rhythmic genes, Cluster: 3
## n(genes) = 451
## 
## [1] "Loading annotation file for Beauveria bassiana"
## [1] "Done."
## [1] "Number of genes in background geneset: 9006"
## [1] "Number of genes in the test set: 451"
## [1] "--------------------------------"
## [1] "Number of GO terms in background geneset: 2453"
## [1] "Number of GO terms (at least 5genes) in background geneset: 898"
## [1] "Number of GO terms (at least 5genes) in test set: 164"
## [1] "Testing for enrichment..."
## 
## n(overrepresented terms) = 16

## Species: beau
## 24h-rhythmic genes, Cluster: 4
## n(genes) = 324
## 
## [1] "Loading annotation file for Beauveria bassiana"
## [1] "Done."
## [1] "Number of genes in background geneset: 9006"
## [1] "Number of genes in the test set: 324"
## [1] "--------------------------------"
## [1] "Number of GO terms in background geneset: 2453"
## [1] "Number of GO terms (at least 5genes) in background geneset: 898"
## [1] "Number of GO terms (at least 5genes) in test set: 177"
## [1] "Testing for enrichment..."
## 
## n(overrepresented terms) = 95

## Species: ophio_cflo
## 24h-rhythmic genes, Cluster: 1
## n(genes) = 718
## 
## [1] "Loading annotation file for Ophiocordyceps camponoti-floridani"
## [1] "Done."
## [1] "Number of genes in background geneset: 6998"
## [1] "Number of genes in the test set: 718"
## [1] "--------------------------------"
## [1] "Number of GO terms in background geneset: 2359"
## [1] "Number of GO terms (at least 5genes) in background geneset: 831"
## [1] "Number of GO terms (at least 5genes) in test set: 269"
## [1] "Testing for enrichment..."
## 
## n(overrepresented terms) = 153

## Species: ophio_cflo
## 24h-rhythmic genes, Cluster: 2
## n(genes) = 1026
## 
## [1] "Loading annotation file for Ophiocordyceps camponoti-floridani"
## [1] "Done."
## [1] "Number of genes in background geneset: 6998"
## [1] "Number of genes in the test set: 1026"
## [1] "--------------------------------"
## [1] "Number of GO terms in background geneset: 2359"
## [1] "Number of GO terms (at least 5genes) in background geneset: 831"
## [1] "Number of GO terms (at least 5genes) in test set: 269"
## [1] "Testing for enrichment..."
## 
## n(overrepresented terms) = 131

## Species: ophio_cflo
## 24h-rhythmic genes, Cluster: 3
## n(genes) = 451
## 
## [1] "Loading annotation file for Ophiocordyceps camponoti-floridani"
## [1] "Done."
## [1] "Number of genes in background geneset: 6998"
## [1] "Number of genes in the test set: 451"
## [1] "--------------------------------"
## [1] "Number of GO terms in background geneset: 2359"
## [1] "Number of GO terms (at least 5genes) in background geneset: 831"
## [1] "Number of GO terms (at least 5genes) in test set: 162"
## [1] "Testing for enrichment..."
## 
## n(overrepresented terms) = 35

## Species: ophio_cflo
## 24h-rhythmic genes, Cluster: 4
## n(genes) = 324
## 
## [1] "Loading annotation file for Ophiocordyceps camponoti-floridani"
## [1] "Done."
## [1] "Number of genes in background geneset: 6998"
## [1] "Number of genes in the test set: 324"
## [1] "--------------------------------"
## [1] "Number of GO terms in background geneset: 2359"
## [1] "Number of GO terms (at least 5genes) in background geneset: 831"
## [1] "Number of GO terms (at least 5genes) in test set: 176"
## [1] "Testing for enrichment..."
## 
## n(overrepresented terms) = 77

Overlap b/n clusters and rhy24

## Visualize the overlap

cluster.dat <- list()
for (i in 1:n_clusters) {
    cluster.dat[[i]] <- my_gene_col %>% 
rownames_to_column("g") %>% filter(cluster==as.character(i)) %>% pull(g)
}
names(cluster.dat) <- paste0("Cluster_",1:4)

for (j in 1:2) {
    
    rhy.dat <- rhy[[j]]
    cluster.dat.dummy <- cluster.dat
    
    if (j == 1) {
      for (i in 1:n_clusters) {
        cluster.dat.dummy[[i]] <- 
            homology.dat %>% 
            filter(ophio_gene %in% cluster.dat.dummy[[i]]) %>% 
            pull(beau_gene)
      }
    }
    
    listInput <- list(rhy.dat, 
                      cluster.dat.dummy[[1]], cluster.dat.dummy[[2]], 
                      cluster.dat.dummy[[3]], cluster.dat.dummy[[4]])
    names(listInput) <- c(paste0(sample.name[[j]], c("_rhy24")), paste0("cluster_",1:4))
    
    library(UpSetR)
    library(viridis)
    # caste.col <- c("#F23030","#1A80D9")
    upset(fromList(listInput), 
          number.angles = 0, point.size = 3, line.size = 1.5, 
          mainbar.y.label = "Number of overlapping genes", 
          sets.x.label = "Sig. rhy genes", 
          text.scale = c(1.5, # y-axis label ("# overlapping genes")
                         2, # y-axis tick labels ("1000, 2000,..")
                         1.5, # label for histogram ("sig. rhy genes")
                         1, # tick labels for histogram
                         1.5, # set names ("Cflo-brain_08h,..") 
                         1.5),
          sets = names(listInput),
          nintersects = 15,
          keep.order = T,
          sets.bar.color = viridis(1),
          # adding queries
          query.legend = "bottom"
          ) %>% 
      print()
  
}

It seems that majority of the genes in Cluster 3 and 4 are sig. rhythmic in Ophio but not in Beau. We will perform the pairwise Fisher’s exact test to find out. Let’s dig in!

NOTE: We need to think about the best way to perform the Fisher’s exact test. For starters, I am transforming all the gene names to Ophio

# LIST ONE - Cluster identity
list1 <- cluster.dat
names(list1) <- names(cluster.dat)

## LIST TWO - ophio rhythmic genes
beau.ortho.rhy <- homology.dat %>% filter(beau_gene %in% rhy[[1]]) %>% pull(ophio_gene) %>% unique() 
ocflo.ortho.rhy <- homology.dat %>% filter(ophio_gene %in% rhy[[2]]) %>% pull(ophio_gene) %>% unique()
list2 <- list(beau.ortho.rhy, ocflo.ortho.rhy)
names(list2) <- paste0(sample.name[1:2], c("_24h"))

## CHECK FOR OVERLAP
library(GeneOverlap)

# define the background geneset 
# in our case, it would be the number of orthologous genes between beau and Ophio_cflo
nGenes = homology.dat %>% pull(ophio_gene) %>% unique() %>% length()

## make a GOM object
gom.1v2 <- newGOM(list1, list2, genome.size = nGenes)
png(paste0(path_to_repo, "/results/figures/BD/ocflo_beau_orthologs_rhy_overlap.png"),
    width = 15, height = 15, units = "cm", res = 300)
drawHeatmap(gom.1v2,
              adj.p=T,
              cutoff=0.01,
              what="odds.ratio",
              # what="Jaccard",
              log.scale = T,
              note.col = "grey60")
trash <- dev.off()
Orthologous rhy24 genes

Orthologous rhy24 genes

As we predicted, Cluster 3 and 4 genes show a stronger overlap with 24h-rhythmic genes in O. cflo as comapred to Beauveria (as can be seen from both log2-odds ratio and the associated q-value). The signal is strongest for Cluster 4, so let’s see which genes are in this cluster.

Cluster-4 genes

## Get the annotation data
ocflo.annots <- read.csv(paste0(path_to_repo, "/data/ophio_cflo_TC6_data.csv"), stringsAsFactors = F)
ocflo.annots %<>% 
  as.tibble() %>%
  filter(expressed=="yes") %>%
  select(gene_name = gene_ID_ncbi, gene_ID_robin, blast_annot, GammaP_24h, GOs:ophio_kim_homolog)

## Subset the gene_names
ocflo.annots %>% 
  filter(gene_name %in% cluster.dat[[4]]) %>%
  
  # # plot the q-values
  # ggplot() + 
  # geom_density(aes(x=GammaP_24h)) +
  # labs(x="rhythmicity, 24h (q-value)") +
  # scale_x_continuous(breaks = c(0,0.05, 0.1, 0.5, 1)) +
  # theme_Publication()
  
  filter(!is.na(GOs)) %>% 
  view()


## Check these genes for other annotations (signalP, SSP, TMHMM)
# LIST ONE - Cluster identity
list1 <- cluster.dat
names(list1) <- names(cluster.dat)

## LIST TWO - ophio rhythmic genes
signalP <- ocflo.annots %>% filter(signalP == "yes") %>% pull(gene_name)
SSP <- ocflo.annots %>% filter(SSP == "yes") %>% pull(gene_name)
TMHMM <- ocflo.annots %>% filter(TMHMM == "yes") %>% pull(gene_name)
list2 <- list(signalP, SSP, TMHMM)
names(list2) <- paste0(sample.name[[2]], "-", c("signalP", "SSP", "TMHMM"))

## CHECK FOR OVERLAP
library(GeneOverlap)

# define the background geneset 
# in our case, it would be the number of orthologous genes between beau and Ophio_cflo
nGenes = ocflo.annots %>% nrow() 

## make a GOM object
gom <- newGOM(list1, list2, genome.size = nGenes)
png(paste0(path_to_repo, "/results/figures/BD/ocflo_beau_orthologs_annots_overlap.png"),
    width = 15, height = 15, units = "cm", res = 300)
drawHeatmap(gom,
              adj.p=T,
              cutoff=0.01,
              what="odds.ratio",
              # what="Jaccard",
              log.scale = T,
              note.col = "grey60")
trash <- dev.off()
Overlap of orthologous rhy24 gene clusters with additional annotations

Overlap of orthologous rhy24 gene clusters with additional annotations

4. Ophio DEGs during infection

Do prep for analyses

Prepare the functions, libraries required

# Let's load functions for running limorhyde
source(system.file('extdata', 'vignette_functions.R', package = 'limorhyde'))
# Let's load the libraries required for running Limorhyde
# library('annotate')
library('data.table')
library('foreach')
# library('GEOquery')
library('ggplot2')
library('knitr')
library('limma')
library('limorhyde')

conflict_prefer("union", "dplyr")

Format metadata

Create dataframe with metadata information for the different samples collected

sampleName <- c("ophio_cflo","ophio_ophio-infected")
short.name <- c("AC","AI") # AC = arb2-control, AI = arb2-infection
time.points <- c(2,4,6,8,10,12,14,16,18,20,22,24)
light.dark <- c(rep("light",times=5), rep("dark",times=6), rep("light", times=1))

meta <- data.frame(title = paste0(rep(sampleName, each=12),"_ZT",time.points),
                       sample = paste0(rep(time.points, times=2),rep(short.name, each=12)),
                       genotype = rep(sampleName, each=12),
                       time = rep(time.points, times=2),
                       cond = rep(sampleName, each=12),
                       LD = rep(light.dark, times=2),
                       stringsAsFactors = F)

meta %>% glimpse()
## Observations: 24
## Variables: 6
## $ title    <chr> "ophio_cflo_ZT2", "ophio_cflo_ZT4", "ophio_cflo_ZT6", "ophio…
## $ sample   <chr> "2AC", "4AC", "6AC", "8AC", "10AC", "12AC", "14AC", "16AC", …
## $ genotype <chr> "ophio_cflo", "ophio_cflo", "ophio_cflo", "ophio_cflo", "oph…
## $ time     <dbl> 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 2, 4, 6, 8, 10, …
## $ cond     <chr> "ophio_cflo", "ophio_cflo", "ophio_cflo", "ophio_cflo", "oph…
## $ LD       <chr> "light", "light", "light", "light", "light", "dark", "dark",…

Now, format the metadata.

### 1.1.1 Format the meta-data ----------------
# load the meta-data
sm <- meta
# Let's format the columns in the right data-type
sm$time <- as.numeric(sm$time)
# sm$batch <- as.factor(sm$batch)
sm$LD <- as.factor(sm$LD)
# sm$location <- as.factor(sm$location)

# Let's get a glimpse of the metadata
sm %>% as_tibble() %>% head()
## # A tibble: 6 x 6
##   title           sample genotype    time cond       LD   
##   <chr>           <chr>  <chr>      <dbl> <chr>      <fct>
## 1 ophio_cflo_ZT2  2AC    ophio_cflo     2 ophio_cflo light
## 2 ophio_cflo_ZT4  4AC    ophio_cflo     4 ophio_cflo light
## 3 ophio_cflo_ZT6  6AC    ophio_cflo     6 ophio_cflo light
## 4 ophio_cflo_ZT8  8AC    ophio_cflo     8 ophio_cflo light
## 5 ophio_cflo_ZT10 10AC   ophio_cflo    10 ophio_cflo light
## 6 ophio_cflo_ZT12 12AC   ophio_cflo    12 ophio_cflo dark
# Next we use limorhyde to calculate time_cos and time_sin, which are based on the first
#harmonic of a Fourier decomposition of the time column, and append them to the sm data frame.
sm = cbind(sm, limorhyde(sm$time, 'time_'))
# convert the dataframe into a data.table
sm <- data.table(sm)
# check that it worked
sm[1:5, ]
##              title sample   genotype time       cond    LD      time_cos
## 1:  ophio_cflo_ZT2    2AC ophio_cflo    2 ophio_cflo light  8.660254e-01
## 2:  ophio_cflo_ZT4    4AC ophio_cflo    4 ophio_cflo light  5.000000e-01
## 3:  ophio_cflo_ZT6    6AC ophio_cflo    6 ophio_cflo light  6.123234e-17
## 4:  ophio_cflo_ZT8    8AC ophio_cflo    8 ophio_cflo light -5.000000e-01
## 5: ophio_cflo_ZT10   10AC ophio_cflo   10 ophio_cflo light -8.660254e-01
##     time_sin
## 1: 0.5000000
## 2: 0.8660254
## 3: 1.0000000
## 4: 0.8660254
## 5: 0.5000000

load data

## DATASET 1
## Load the control O.cflo data (from TC6)
ocflo.control.dat <-
  data.db %>% 
  tbl(., paste0(sampleName[[1]], "_fpkm")) %>% 
  select(gene_name, everything()) %>%
  collect()

## DATASET 2
## Load the O.cflo infection data from the mixed transcriptomics study (from TC7)
inf.db <- dbConnect(RSQLite::SQLite(),
                   paste0(path_to_repo,"/../Das_et_al_2022b/data/databases/TC7_data.db"))
# src_dbi(inf.db)
# extract the (gene-expr X time-point) data
ocflo.inf.dat <-
  inf.db %>%
  tbl(., paste0(sampleName[[2]], "_fpkm")) %>%
  select(gene_name, everything()) %>%
  collect()

filter data

The goal is to use only the genes that show expression (>1 FPKM) for at least half of the timepoints during the 24h day (i.e., 6 of the 12 timepoints).

## DATASET 1
n.exp.1 <- apply(ocflo.control.dat[-1], 1, function(x) sum(x>=1))
ocflo.control.dat <- ocflo.control.dat[which(n.exp.1>=6),]
colnames(ocflo.control.dat)[-1] <- paste0("ZT", meta[meta$cond==sampleName[[1]],] %>% pull(sample))

## DATASET 2
n.exp.2 <- apply(ocflo.inf.dat[-1], 1, function(x) sum(x>=1))
ocflo.inf.dat <- ocflo.inf.dat[which(n.exp.2>=6),]
colnames(ocflo.inf.dat)[-1] <- paste0("ZT", meta[meta$cond==sampleName[[2]],] %>% pull(sample))

## Use the genes that are expressed in both conditions
emat <-
  ocflo.control.dat %>% 
  filter(gene_name %in% ocflo.inf.dat$gene_name) %>% 
  left_join(ocflo.inf.dat, by="gene_name") %>% 
  as.data.frame()

Run analyses

Next, let’s perform the DEG analyses for the ophio-cflo (halfway through infection v. controls)

### Convert to a matrix

# save gene names as row names
rownames(emat) <- emat[,1]
emat <- emat[,-1]
# Need to make the emat into a matrix.
emat <- data.matrix(emat)
# log2 transform the data
emat <- log2(emat + 1)


### Set thresholds
# Set threshold for q-value and log2FC
q.threshold <- 0.05 # currently, using 5% FDR (BH adjusted p-value)
log2.foldchange <- 1 # thus, any gene with a 2^(log2.foldchange) fold change in it's expression

### Format the metadata, if necessary
# Filter the metadata according to your comparison
sm.sub <- sm %>% filter(cond %in% c(sampleName))
# Define the cond column as a factor
sm.sub$cond <- as.factor(sm.sub$cond)

### Let's run the DEG analyses
# Use the subsetted emat to find DEGs
design.deg = model.matrix(~ cond + time_cos + time_sin, data = sm.sub)
#
fit = lmFit(emat, design.deg)
fit = eBayes(fit, trend = TRUE)
# Take a look at the coefficients table
# fit$coefficients %>% head()
#
deLimma.deg = data.table(topTable(fit, coef = 2, number = Inf), keep.rownames = TRUE)
setnames(deLimma.deg, 'rn', 'gene_name')
deLimma.deg[, adj.P.Val := p.adjust(P.Value, method = 'BH')]
setorderv(deLimma.deg, 'adj.P.Val')

### Annotate the results
# Annotate the results to indicate the significant genes
all.DEGs <-
  deLimma.deg %>% 
  arrange(desc(abs(logFC)), adj.P.Val) %>% 
  mutate(sig = as.factor(ifelse(adj.P.Val < q.threshold & abs(logFC) >= log2.foldchange, "yes", "no"))) %>% 
  mutate(inf_v_control = as.factor(ifelse(sig=="yes", ifelse( logFC > 0, "up", "down" ), "NA"))) %>% 
  mutate(inf = sampleName[[2]])

### Summarize the results
writeLines(paste0("\nControl-", sampleName[[1]], " v. ", sampleName[[2]], "\n--Results of DEG analysis--"))
## 
## Control-ophio_cflo v. ophio_ophio-infected
## --Results of DEG analysis--
## How many DEGs - 5% FDR and ≥ 1 fold change in gene expression
all.DEGs %>% 
  # filter(adj.P.Val < q.threshold) %>%
  # filter(abs(logFC) >= 2) %>% # change the criteria here for top DEG or all DEG (logFC≥1)
  filter(sig == "yes") %>% 
  
  # pull(gene_name) %>% 
  
  group_by(inf_v_control) %>% 
  summarise(n_genes = n()) %>% 
  as.data.frame() %>% 
    ## n = 81 up- and 141 down-regulated genes in Cflo heads during Ophio-infection 
    ## (at 5% FDR; log2-fold-change ≥ 1) 
  print()
##   inf_v_control n_genes
## 1          down     395
## 2            up     318
### Subset to keep only sig. DEGs
sig.DEGs <- all.DEGs %>% filter(sig=="yes")

Visualize results

# Volcano plot 
library(viridis)

ggplot(all.DEGs) +
  # geom_hline(yintercept = -log10(0.05), col="red", alpha=0.6) +
  # geom_vline(xintercept = c(-2,2), col="grey60", alpha=0.75) +
  geom_point(aes(x = logFC, y = -log10(adj.P.Val), color=sig), size = 1.5, alpha = 0.5) +
  labs(x = expression(log[2]*' fold-change (inf_v_control)'), 
       y = expression(-log[10]*' '*q[DE]),
       title = "O.cflo (infection v. control)",
       color = "significant") +
  # scale_x_continuous(limits = c(-5,3),
  #                    breaks = c(-5,-4,-3,-2,-1,0,1,2,3),
  #                    labels = c("-5","","-3","","-1","","1","","3")) +
  # xlim(c(-50,50)) +
  theme_Publication() +
  scale_color_viridis(discrete = T, direction = -1, option = "viridis")

Load manip data

## Load the ophio DEG (at manipulation) data from Will et al. 2020
will2020_data <- read.csv(paste0(path_to_repo,"/data/input/ophio_cflo/complete_annotations/FullBlast_EC05_RNAseq_orignal_copy_26Aug19.csv"), stringsAsFactors = F)
will2020_data %<>% 
  as_tibble() %>% 
  filter(sample_1=="Alive" & sample_2=="Fungus") %>%
  select(arb2_gene, logFC = log2.fold_change., q_value, significant) %>% 
  mutate(logFC=as.numeric(logFC), q_value=as.numeric(q_value)) %>%
  filter(significant=="yes") %>% 
  mutate(up_down = ifelse(logFC > 0, "down", "up")) %>%
  mutate(logFC = -1*logFC) %>% 
  na.omit()

### Change ophio gene names to ncbi IDs
will2020_data %<>% 
  left_join(ocflo.annots[1:3], by=c("arb2_gene"="gene_ID_robin")) %>%
  select(-1) %>% 
  select(gene_name, blast_annot, everything())

5. Overlap between DEGs during infection v. manipulation

### Subset the up/down-regulated genes
### At halfway-through disease progression
inf.up <- sig.DEGs %>% filter(inf_v_control=="up") %>% pull(gene_name)
inf.down <- sig.DEGs %>% filter(inf_v_control=="down") %>% pull(gene_name)
### At active manipulation
manip.up <- will2020_data %>% filter(up_down=="up") %>% pull(gene_name)
manip.down <- will2020_data %>% filter(up_down=="down") %>% pull(gene_name)


### Visualize the results
listInput <- list(inf.up, inf.down, manip.up, manip.down)
names(listInput) <- c(paste0("inf_",c("up","down")), paste0("manip_", c("up","down")))
    
library(UpSetR)
library(viridis)
upset(fromList(listInput), 
  number.angles = 0, point.size = 3, line.size = 1.5, 
  mainbar.y.label = "Number of overlapping genes", 
  sets.x.label = "Sig. DE genes", 
  text.scale = c(1.5, # y-axis label ("# overlapping genes")
                 2, # y-axis tick labels ("1000, 2000,..")
                 1.5, # label for histogram ("sig. rhy genes")
                 1, # tick labels for histogram
                 1.5, # set names ("Cflo-brain_08h,..") 
                 1.5),
  sets = names(listInput),
  nintersects = 15,
  keep.order = T,
  sets.bar.color = viridis(1),
  # adding queries
  query.legend = "bottom"
  ) %>% 
print()

### Test significance of overlap
list1 <- list(inf.up, inf.down)
names(list1) <- paste0("inf_",c("up","down"))
list2 <- list(manip.up, manip.down)
names(list2) <- paste0("manip_", c("up","down"))
bg.genes <- all.DEGs %>% nrow()

overlap <- check_overlap(list1, list2, bg.genes)

## $rowInd
## [1] 2 1
## 
## $colInd
## [1] 1 2
## 
## $call
## heatmap.2(x = plot.mat, Rowv = NA, Colv = NA, dendrogram = "none", 
##     scale = "none", col = brewer.pal(ncolused, grid.col), colsep = col_sep, 
##     rowsep = row_sep, sepcolor = "white", sepwidth = c(0.002, 
##         0.002), cellnote = note.mat, notecex = 1.6, notecol = note.col, 
##     trace = "none", margins = margins_use, cexRow = row_cexrc, 
##     cexCol = col_cexrc, key = T, keysize = key_size, density.info = "none", 
##     main = main.txt, xlab = footnote)
## 
## $carpet
##            inf_down   inf_up
## manip_up    0.00000 2.075416
## manip_down  1.20292 0.000000
## 
## $rowDendrogram
## 'dendrogram' with 2 branches and 2 members total, at height 1.414214 
## 
## $colDendrogram
## 'dendrogram' with 2 branches and 2 members total, at height 1.414214 
## 
## $breaks
##  [1] 0.0000000 0.2306017 0.4612035 0.6918052 0.9224070 1.1530087 1.3836105
##  [8] 1.6142122 1.8448140 2.0754157
## 
## $col
## [1] "#F7FCF5" "#E5F5E0" "#C7E9C0" "#A1D99B" "#74C476" "#41AB5D" "#238B45"
## [8] "#006D2C" "#00441B"
## 
## $colorTable
##         low      high   color
## 1 0.0000000 0.2306017 #F7FCF5
## 2 0.2306017 0.4612035 #E5F5E0
## 3 0.4612035 0.6918052 #C7E9C0
## 4 0.6918052 0.9224070 #A1D99B
## 5 0.9224070 1.1530087 #74C476
## 6 1.1530087 1.3836105 #41AB5D
## 7 1.3836105 1.6142122 #238B45
## 8 1.6142122 1.8448140 #006D2C
## 9 1.8448140 2.0754157 #00441B
## 
## $layout
## $layout$lmat
##      [,1] [,2]
## [1,]    4    3
## [2,]    2    1
## 
## $layout$lhei
## [1] 1.485097 4.000000
## 
## $layout$lwid
## [1] 1.485097 4.000000